agentsclimarketplace

Gdc vtt to note

Skill ihybrd/my_ai_skills/gdc-vtt-to-note

AI Skills

Install
npx -y skills add ihybrd/my_ai_skills --skill gdc-vtt-to-note

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

When the user provides a GDC VTT segment URL, run the bundled capture script to merge captions, then summarize and create an Obsidian note under gdc summary.

SKILL.md

2.0 KB, 472 tokens by cl100k_base, as published. Nobody here has run it

GDC VTT To Note Skill

Purpose

Use this skill when a user wants to turn a GDC talk caption stream into:

  1. A merged caption file.
  2. A short structured summary.
  3. An Obsidian note in literature notes/video notes/gdc/ai notes.

Trigger

  • User provides a GDC caption .vtt segment URL.

Required Input

  • One GDC VTT segment URL, for example: .../index_4_0_33.vtt

Do not

download the provided vtt file directly, instead, run the bundled script to process it and generate a caption file (captions.txt). Then read the generated caption file to create the summary and note.

Script Execution

run the script with the provided VTT segment URL. For example: python3 gdc-vtt-to-note/scripts/capture_gdc_vtt.py $vtt_url_provided_by_user

Post-Processing Workflow

this section will be exectuted only when the script stops running and generates a caption file (captions.txt). If the script fails, report the error and do not proceed.

once the script successfully generates a caption file (captions.txt), do the following:

  1. Read the generated caption file.
  2. Build a concise summary including:
    • Topic
    • Key points
    • Actionable insights
  3. Create an Obsidian note in literature notes/video notes/gdc/ai notes.

Note Naming Rule

  • Filename format: YYYY-MM-DD-{summary_slug}.md
  • Slug rules:
    • lowercase
    • spaces -> -
    • remove invalid filename characters
  • If conflict exists, append -2, -3, etc.

Note Content

Include:

  • Title
  • Source VTT URL
  • Caption file path
  • Summary sections
  • Captions.txt full content as reference

Prefer frontmatter metadata:

  • source_vtt
  • caption_file
  • created_at
  • tags: [gdc, summary]

Safety

  • If script execution fails, report stderr and do not create the note.
  • If caption file is empty, create note with incomplete status.
  • Prefer absolute paths in command execution and output reporting.

Gives 0 of the 12 instructions most note taking skills give in 472 tokens

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-06

  • include a visual element on every slidein 44 of 686, across 13 files
  • use wikilinks for internal vault linksin 35 of 686, across 11 files
  • commit to a single visual motif across every slidein 34 of 686, across 9 files
  • read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
  • keep 0.5 inch minimum marginsin 30 of 686, across 7 files
  • use subagents to visually inspect rendered slidesin 30 of 686, across 6 files
  • re-verify affected slides after every fixin 27 of 686, across 5 files
  • run content QA checks before declaring successin 26 of 686, across 3 files
  • Use Markdown links for external URLs onlyin 26 of 686, across 10 files
  • pick a bold topic specific color palettein 24 of 686, across 2 files
  • read editing guide before editing existing presentationsin 23 of 686, across 1 file
  • use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

  • Run the bundled capture script with the provided VTT URL
  • Wait for the script to generate a caption file
  • Read the generated caption file
  • Build a concise summary including topic and key points
  • Create an Obsidian note under the gdc ai notes directory
  • Name the note using the current date and summary slug

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.